Expert Data Modeler, Fraud Risk Detection

This is a fully remote position, open to applicants in California.

📋 Description

• Conduct exploratory analysis and develop fraud labels using extensive datasets.

• Detect fraud patterns, attack strategies, and behavioral indicators.

• Convert fraud and risk challenges into hypotheses, analytical frameworks, model specifications, and measurable success metrics.

• Create machine learning models for detecting account opening fraud, account takeover, and identity risk.

• Assess model performance using ROC/AUC/KS/Gini, precision/recall, fraud capture rate, false-positive rate, customer friction, and the amount of fraud losses averted.

• Develop and validate predictive features utilizing identity, transactional, consumer credit history, device, behavioral, temporal, velocity, network, and third-party data.

• Write clean, efficient, and well-tested code in Python and PySpark.

• Work collaboratively with teams to implement models and features in batch, retro, or real-time decision-making environments.

• Track feature quality, model performance, population shifts, and changes in fraud patterns.

• Design and deliver analyses that detail model performance, trade-offs, risks, and recommendations.

• Adhere to data privacy standards, model documentation, explainability, validation, and governance protocols.

• Report directly to the Senior Manager of Fraud Analytics.

⛳️ Requirements

• A minimum of 3 years of experience in data science, machine learning, statistical modeling, or a closely related quantitative discipline.

• Bachelor's or advanced degree in computer science, statistics, engineering, data science, or another quantitative field.

• Proven experience in developing fraud-detection, identity-risk, credit-risk, financial crime, or other adversarial risk models.

• Demonstrated ability to create impactful fraud features.

• Proficient in Python and PySpark.

• Experience in writing modular and well-tested code for large datasets and distributed or cloud-based data systems.

• Familiarity with pandas, NumPy, scikit-learn, XGBoost, TensorFlow, or similar technologies.

• Understanding of supervised learning, model evaluation, feature selection, statistical inference, experimentation, and model calibration.

• Experience in managing class imbalance, delayed or incomplete labels, evolving attack patterns, and model drift.

• Experience in deploying models into production, either directly or in close collaboration with engineering teams.

🏝️ Benefits

• Competitive compensation package and bonus structure.

• Medical, dental, and vision insurance.

• 401K matching.

• Flexible work environment with options for remote, hybrid, or in-office work.

• Flexible time off, including volunteer time, vacation, sick leave, and 12 paid holidays.

• Variable pay opportunities.

• Comprehensive benefits package.

• An inclusive and purpose-driven culture.